arXiv 18 Mar 2026 · Econometrics
arXiv:2603.17381 · PDF · DOI · OpenAlex · Extracted main text
AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics workflow and adds a post-search holdout evaluation. In a forecast-combination illustration, multiple independent agent runs outperform standard benchmarks in the original rolling evaluation, but not all continue to do so on a post-search holdout. Logged search and holdout evaluation together make adaptive specification search more transparent and help distinguish robust improvements from sample-specific discoveries.
appendix boundary found by appendix_command · 29% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Diebold, Francis X. and Shin, Minchul (2019) Machine Learning for Regularized Survey Forecast Combination: Partially-Egalitarian LASSO and Its Derivatives self | 0.874 | 12 | 7 | 67% |
| 2 | Karpathy, Andrej (2026) autoresearch | 0.644 | 4 | 2 | 50% |
| 3 | Novikov, Alexander and Vũ, Ngân and Eisenberger, Marvin and Dupont,… (2025) AlphaEvolve: A coding agent for scientific and algorithmic discovery | 0.644 | 2 | 2 | 100% |
| 4 | Shin, Minchul and Schor, Nathan (2026) ForeComp: An R Package for Comparing Predictive Accuracy Using Fixed-Smoothing Asymptotics self | 0.511 | 3 | 2 | 33% |
| 5 | Aygün, Eser and Belyaeva, Anastasiya and Comanici, Gheorghe and Cora… (2025) An AI System to Help Scientists Write Expert-Level Empirical Software | 0.405 | 1 | 1 | 100% |
| 6 | Nam, Jaehyun and Yoon, Jinsung and Chen, Jiefeng and Sinha, Raj and… (2025) DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries | 0.405 | 1 | 1 | 100% |
| 7 | Dawid, Herbert and Harting, Philipp and Wang, Hankui and Wang, Zhong… (2025) Agentic Workflows for Economic Research: Design and Implementation | 0.405 | 1 | 1 | 100% |
| 8 | Gelman, Andrew and Loken, Eric (2013) The Garden of Forking Paths: Why Multiple Comparisons Can Be a Problem, Even When There Is No “Fishing Expedition” or “p-Hacking… | 0.405 | 1 | 1 | 100% |
| 9 | Gottweis, Juraj and Weng, Wei-Hung and Daryin, Alexander and Tu, Tao… (2025) Towards an AI co-scientist | 0.405 | 1 | 1 | 100% |
| 10 | Korinek, Anton (2025) AI Agents for Economic Research | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 14 scored citations.